Revisiting Group Robustness: Class-specific Scaling is All You Need
Lists
Only you see this
Abstract
Group distributionally robust optimization, which aims to improve robust accuracies such as worst-group or unbiased accuracy, is one of the mainstream algorithms to mitigate spurious correlation and reduce dataset bias. While existing approaches have apparently gained performance in robust accuracy, these improvements mainly come from a trade-off at the expense of average accuracy. To address the challenges, we first propose a simple class-specific scaling strategy to control the trade-off between robust and average accuracies flexibly and efficiently, which is directly applicable to existing debiasing algorithms without additional training; it reveals that a naive ERM baseline matches or even outperforms the recent debiasing approaches by adopting the class-specific scaling. Then, we employ this technique to 1) evaluate the performance of existing algorithms in a comprehensive manner by introducing a novel unified metric that summarizes the trade-off between the two accuracies as a scalar value and 2) develop an instance-wise adaptive scaling technique for overcoming the trade-off and improving the performance even further in terms of both accuracies. Experimental results verify the effectiveness of the proposed frameworks in both tasks.
BibTeX
@inproceedings{seo2023revisiting,
author = {Seonguk Seo and Bohyung Han},
title = {{Revisiting Group Robustness: Class-specific Scaling is All You Need}},
booktitle = {International Conference on Learning Representations},
year = {2023},
url = {https://openreview.net/forum?id=pkgVPeL9gpX},
}